@davila7

systematic-debugging provides a four-phase methodology for finding root causes before attempting fixes: investigation, pattern analysis, hypothesis testing, and implementation. includes red flags, architectural failure detection, and recovery paths for stuck investigations.

agent-development provides structured guidance for building autonomous claude subprocesses, covering frontmatter schema, system prompt patterns, triggering semantics, and validation rules with concrete examples and reference templates.

peft-fine-tuning enables parameter-efficient adaptation of 7B-70B models using LoRA, QLoRA, and 25+ methods, reducing trainable parameters to <1% while fitting on consumer GPUs. covers ranked configuration, multi-adapter serving, and integration with trl/axolotl/vllm.

outlines guarantees valid structured output (json, xml, regex, code) during generation via finite state machine token filtering, with native pydantic support and zero-overhead inference across local backends like transformers and vllm.

jira skill provides dual-backend natural language interaction (cli and atlassian mcp) with explicit backend detection, issue workflows, and safety constraints. covers creation, search, transition, and comment operations with deliberate safeguards against common failure modes.

commit enforces sentry's conventional message format with type-scoped headers, structured body and footer sections, and issue reference patterns. covers most common commit types and provides worked examples.

huggingface-accelerate abstracts distributed pytorch training (ddp, deepspeed, fsdp, megatron) behind a minimal api, requiring only four lines of code changes to convert single-gpu scripts. covers multi-gpu, mixed precision, gradient accumulation, and multi-node setups via unified interface.

polars covers dataframe operations via expression api, lazy evaluation, and high-performance i/o for csv/parquet/json. includes joins, aggregations, window functions, and pandas migration patterns with performance tuning guidance.

modal-serverless-gpu covers on-demand gpu access for ml workloads via python-native functions, with sub-second cold starts, auto-scaling to zero, and web endpoint deployment. includes gpu selection patterns, persistent volumes, secrets, and scheduling.

generate-image wraps openrouter image apis (gemini 3 pro, flux.2) for photorealistic and artistic generation plus editing. includes api key setup, model selection guidance, and command examples but lacks explicit failure recovery.

create-plan synthesizes codebase context into a structured, actionable plan with scoped action items, discovery-first ordering, and explicit in/out boundaries. targets coding tasks where users request planning.

bun-development covers setup, package management, built-in apis (http, sqlite, file i/o), testing, bundling, and node.js migration. practical for developers adopting bun as a faster javascript runtime.

mcp-integration covers model context protocol setup across stdio, sse, http, and websocket transports. addresses configuration methods, authentication patterns, tool naming, and security best practices for exposing external services as claude code plugin tools.

instructor wraps llm clients to enforce pydantic validation on structured outputs, automatically retrying failed extractions and supporting streaming across anthropic, openai, and local models.

qa-test-planner generates test plans, manual test cases, regression suites, and bug reports for qa engineers. includes figma design validation workflow and structured templates across all qa deliverables.

api-integration-specialist covers production-ready patterns for third-party api authentication, error handling, retry logic, and security. includes oauth 2.0, jwt, webhook verification, rate limiting, and real-world examples for stripe, twilio, sendgrid.

coding-standards collects typescript, javascript, react and node.js best practices organized by domain (naming, error handling, api design, testing). provides code examples of good and bad patterns but lacks procedural guidance on adoption and enforcement.

chroma is an open-source vector database for rag applications, offering local storage, metadata filtering, and semantic search. supports multiple embedding providers and integrates with langchain and llamaindex.

geopandas extends pandas with geospatial operations on vector data. covers reading/writing shapefiles, geojson, geopackage, spatial joins, overlay operations, and crs management with code examples.

sentence-transformers provides local embedding generation across 5000+ pre-trained models, supporting 100+ languages and domain-specific tasks. suited for rag, semantic search, and clustering without external api dependencies.

ai-wrapper-product covers building differentiated ai products by layering validation, prompt engineering, cost control and output quality assurance around api calls. balances user experience against token economics and addresses common failure modes like hallucination and cost spiraling.

clinicaltrials-database provides public api access to clinicaltrials.gov, enabling trial searches by condition, drug, location, status, and phase with json and csv export capabilities.

skill-installer manages installation of codex skills from curated openai lists or custom github repositories, with support for public and private repos via git or direct download.

copywriting delivers structured conversion-focused copy for marketing pages by gathering audience and product context before writing, then applying clarity-first principles and page-type frameworks to drive specific customer actions.

clip bridges vision and language through zero-shot classification, image-text matching, and semantic search. trainable on 400m image-text pairs, no labeled data required for inference.

pptx covers creation, editing, and content extraction from powerpoint files with opinionated design rules and mandatory qa workflows including visual review and format conversion.

writing-plans constructs detailed implementation roadmaps for engineers unfamiliar with the codebase, breaking multi-step requirements into granular tasks with file locations, test strategy, and commit guidance.

claude-code-guide outlines configuration templates and prompting patterns for steering claude code agent behavior, but lacks concrete decision logic and failure recovery steps.

nestjs-expert covers module architecture, dependency injection, testing with jest/supertest, and database integration. claims to diagnose circular dependencies and resolve configuration problems, but lacks concrete procedural steps and actionable workflows.

notion-knowledge-capture structures conversations into linked notion pages across six content types (decisions, how-tos, faqs, wiki, learning, docs), with templates and deduplication via search and fetch workflows.

prisma-expert handles schema design, migrations, query optimization and relations modeling for postgresql, mysql and sqlite. routes raw sql, infrastructure, and connection pooling concerns to specialists.

server-management teaches operational thinking across process lifecycle, monitoring strategy, and scaling decisions. covers principle-based decision-making rather than command syntax.

pdf-processing-pro provides cli tooling and python examples for pdf extraction, forms, tables, and ocr, with error handling scaffolding but incomplete workflows and vague edge case handling.

ai-agents-architect provides conceptual guidance on autonomous agent design, tool integration, and failure mitigation. covers react loops, plan-and-execute patterns, and multi-agent orchestration without procedural depth.

3d-web-experience covers three.js, react three fiber, spline, and webgl optimization for interactive 3d web products. includes asset pipeline guidance, scroll-driven interactions, and performance anti-patterns but lacks actionable procedural depth.

xlsx handles spreadsheet creation, editing, and analysis across multiple formats with formula preservation, financial modeling color conventions, and error detection via pandas and openpyxl backends.

gdpr-dsgvo-expert outlines regulatory compliance domains and audit frameworks but lacks concrete trigger phrases, actionable procedures, and explicit failure mode handling. suitable as reference material rather than executable skill.

email-composer provides templates and tone guidance for drafting professional emails across common scenarios (requests, follow-ups, technical updates, customer support). lacks procedural clarity on how to adapt templates to novel contexts or handle ambiguous requirements.

excalidraw delegates file operations to subagents to preserve context budget. documents token cost problem (4k-22k per file) and dispatch patterns but lacks concrete implementation steps.

ui-ux-pro-max aggregates design patterns, color palettes, typography, and ux rules across multiple stacks. execution relies on a python search script that may not exist or function as documented, and edge cases are unaddressed.

mui covers material-ui v7 component patterns including sx prop styling, theme integration via hooks, and responsive breakpoint design. lacks procedural depth and actionable examples.

frontend-patterns documents react and next.js component architecture, state management, and performance techniques with code examples but lacks actionable procedures and failure mode discussion.

nextjs-best-practices documents app router fundamentals including server/client component separation, caching layers, and file-based routing conventions, but lacks concrete implementation steps and error handling guidance.

cto-advisor bundles strategic frameworks, python-based tech debt and team scaling tools, adr templates, and metrics guidance for ctos managing technology strategy, team leadership, and architecture decisions across five core responsibilities.

marketing-demand-acquisition outlines multi-channel acquisition tactics (paid media, seo, partnerships) and kpi frameworks for b2b saas, but lacks executable procedure depth and failure mode planning.

nodejs-best-practices covers framework selection, async patterns, architecture layering, and security principles for node.js development. emphasizes decision-making over pattern replication, with decision trees for runtime/framework choices and checklists for validation, error handling, and testing strategy.

citation-management covers paper discovery, metadata extraction, bibtex formatting, and validation across google scholar, pubmed, and arxiv. workflows are scripted but lack explicit error handling and recovery strategies.

security-compliance outlines a six-phase security lifecycle across nine domains (iam, network, data, application, cloud, endpoint, operations, incident response, grc) with decision frameworks for risk assessment, control selection, and compliance choices. includes incident response workflows, vulnerability management, and soc2 audit guidance with timelines and deliverables.

docx handles creation, reading, and editing of word documents with xml-level control and tracked changes support, but procedures remain incomplete and edge cases largely unaddressed.

autogpt-agents provides a visual drag-and-drop platform for building and deploying continuous ai agents with block-based workflows, multiple trigger types, and integration connectors, though execution procedures lack specificity and failure handling is minimal.

literature-review conducts systematic searches across academic databases and synthesizes results into formatted documents, but lacks concrete procedural steps and omits failure handling.

supabase-postgres-best-practices organizes 8 categories of postgres optimization rules with priority levels and sql examples, but lacks concrete procedures for applying rules to live systems.

seo covers technical and on-page optimization via robots.txt, meta tags, canonical urls, xml sitemaps, url structure, https, title/description, heading hierarchy, images, and internal linking. structured data section is incomplete.

ml-paper-writing provides philosophy and high-level guidance for drafting academic papers in machine learning conferences, emphasizing proactive delivery of full drafts and literature search. lacks detailed procedural steps and concrete decision points for execution.

app-store-optimization aggregates aso tactics across keyword research, metadata tuning, competitor analysis, and review management for ios and android. lacks procedural depth and assumes external data sources without addressing practical integration constraints.

stable-diffusion-image-generation wraps huggingface diffusers for text-to-image, inpainting, and outpainting workflows. covers sd 1.5 through flux with lora adapters and scheduler selection, but lacks actionable procedure detail.

backend-to-frontend-handoff-docs guides api documentation creation for frontend consumption, covering context transfer, endpoint specs, and validation rules. trigger coverage is narrow and language is often generic rather than prescriptive about what goes in each section.

sympy handles symbolic mathematics in python including equation solving, calculus, linear algebra, and expression simplification. covers exact computation where numerical approximations fail.

spreadsheet covers creation, editing, analysis, and visualization of xlsx/csv/tsv files using openpyxl and pandas, with basic workflow guidance for layout validation and formula handling.

research-engineer enforces scientific rigor and rejects invalid problem constraints. prioritizes theoretical correctness over convenience, with explicit protocols against hallucination and oversimplification. incomplete procedural coverage limits real-world applicability.

mermaid-diagrams covers text-based software diagramming (class, sequence, flowchart, erd, c4, state, git, gantt, charts) with version-control friendly syntax and multi-platform native support. references and best practices included.

research-grants describes federal grant writing for NSF, NIH, DOE, and DARPA with emphasis on persuasive structure and agency-specific criteria. lacks concrete procedures and executable steps.

behavioral-modes defines seven operational modes (brainstorm, implement, debug, review, teach, ship, explore) for task-specific ai adaptation, including trigger detection and multi-agent collaboration patterns, but lacks formal decision trees and explicit failure recovery.

agent-evaluation addresses behavioral testing and reliability metrics for llm agents, emphasizing statistical rigor and adversarial probing over single-run benchmarks to catch production failures.

scientific-slides generates visually-led presentation decks with ai-rendered slides, research citations, and configurable formats for conferences, defenses, and grant pitches. workflow integrates with research lookup and outputs pdf, powerpoint, or beamer formats.

backend-patterns documents rest api url conventions and http verb mappings. content is incomplete, lacking concrete procedures, error handling, and decision logic needed for production backend work.

seo-fundamentals outlines e-e-a-t principles, core web vitals targets, and technical seo checklist items for search visibility, but lacks procedural depth and actionable recovery patterns.

latex-posters covers creation of research posters for academic conferences using beamerposter, tikzposter, or baposter packages. guidance addresses layout, typography, color schemes, and multi-column designs with integration of figures and citations.

code-review-checklist provides a categorized framework for conducting code reviews spanning functionality, security, performance, and maintainability, though the procedure remains incomplete and lacks concrete decision criteria.

it-operations outlines principles for infrastructure management, monitoring, and incident response but lacks concrete procedures, specific trigger phrases, and actionable decision trees needed for reliable execution.

architecture covers the conceptual groundwork of requirements analysis and trade-off evaluation but lacks procedural depth and actionable decision workflows. useful as a conceptual reference, not as executable guidance.

seo-audit provides a framework for identifying crawlability, indexation, and on-page seo issues with site-type-specific guidance, but lacks concrete procedural steps and fails to address recovery from common failure modes.

code-reviewer wraps multi-language linting and static analysis via python scripts, supporting typescript, javascript, python, swift, kotlin, and go. lacks actionable review workflow, error handling, and concrete output contracts.

scientific-writing covers imrad-structured manuscript composition with citation integration and reporting standard guidance. procedure is underspecified, lacking step-by-step execution detail and failure mode handling.

scientific-brainstorming offers conversational ideation through five phases (context, divergence, connection, evaluation, synthesis) with structured techniques like scamper and triz. lacks concrete step-by-step procedure and failure mode coverage.

writing-skills documents a tdd-inspired approach to skill authoring, emphasizing test-driven validation of agent behavior against documented procedures before deployment.

treatment-plans offers latex templating for generating medical treatment documentation across specialties with emphasis on conciseness and regulatory alignment, though procedural detail and trigger definition remain underdeveloped.

manim covers programmatic mathematical animation and visualization using python, suitable for creating educational video content with geometric shapes, equations, and scene-based rendering, but lacks actionable procedures.

paper-2-web transforms academic papers into interactive websites and presentation materials through an llm-powered extraction and design pipeline. output includes explorable homepages, video presentations, and conference posters.

statistical-analysis describes a toolkit for hypothesis testing, regression, and bayesian methods with apa reporting, but lacks actionable procedures and concrete implementation guidance.

content-research-writer guides collaborative outlining and iterative refinement of written content. it manages citations across formats, preserves authorial voice, and delivers section-by-section feedback on clarity, flow, and evidence quality.

plotly is a visualization library offering 40+ chart types via two apis: express for quick plots and graph objects for fine control. covers basic statistical scientific financial and geographic charts with interactive html and static image export.

scikit-learn covers classical machine learning workflows including supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), preprocessing, and model evaluation with pipelines for reproducible production deployments.

statsmodels covers regression, glm, time series, and hypothesis testing for statistical inference. lacks procedural depth and specific trigger patterns for cross-vendor integration.

qdrant-vector-search is a rust-based vector database for production rag systems offering hybrid search, multiple distance metrics, quantization, and distributed scaling via sharding and replication.

peer-review outlines a framework for evaluating scientific manuscripts across methodology, statistics, ethics, and reproducibility, though lacks concrete procedural steps and decision logic.

tailwind-patterns documents v4 configuration via css-native @theme directives, container queries, and design token architecture. incomplete procedure coverage and no failure mode discussion limit practical utility.

react-best-practices collects 40+ optimization rules for react and next.js, indexed by impact level. lacks procedural depth and actionable step sequences for applying rules in real codebases.

remotion covers programmatic video creation via react components, frame-based animation, asset handling, text/caption workflows, and data visualization. primarily a reference index rather than executable skill.

task-execution-engine manages implementation work as markdown checkboxes within design documents, providing cli commands to track task status and completion state without external session files.

langgraph covers production-grade ai agent architecture using explicit graph construction, state management, and cycle handling, though concrete implementation patterns remain sparse.

security-review provides a trigger-based framework for identifying security review opportunities across authentication, secrets, api endpoints, and sensitive data handling. procedure depth and edge case coverage are underdeveloped.

json-canvas provides a schema reference for the .canvas file format used in obsidian but lacks actionable procedures, trigger clarity, and edge case coverage for real-world canvas creation and editing.

pytorch-fsdp covers distributed training patterns via the join context manager for handling uneven inputs, with api reference for joinable classes and join hooks but lacks actionable implementation guidance.

best-practices aggregates lighthouse audit standards for web security, compatibility, and code quality. covers https enforcement and related patterns but lacks actionable procedure depth.

pricing-strategy provides conversational guidance on saas pricing models and competitive positioning through structured context gathering, but lacks executable procedures, decision frameworks, or measurable outcomes.

gemini handles large-context code and plan reviews via cli, with explicit warnings about approval modes in non-interactive environments but minimal procedural detail on actual invocation.

lead-research-assistant guides users through lead identification by analyzing business context and searching for target companies, but lacks concrete implementation details and decision logic for ranking or validation.

codex-review provides integration with codex ai for reviewing code and generating changelogs automatically before commits, with minimal procedural guidance and no failure recovery.

long-context documents transformer positional encoding techniques (rope, yarn, alibi, interpolation) for extending model context windows. lacks actionable procedures and failure mode discussion.

senior-prompt-engineer aggregates high-level guidance on prompt patterns, rag optimization, and agentic system design, but lacks procedural depth and concrete decision logic for production use.

senior-security describes three python scripts for threat modeling, security auditing, and penetration testing, but provides no actionable procedures, decision logic, or failure modes. marketing copy without substance.

rag-implementation outlines retrieval-augmented generation principles around chunking and hybrid retrieval but lacks concrete procedures, decision trees, or failure modes. incomplete as written.

product-manager-toolkit bundles RICE scoring, interview analysis, and PRD templates with minimal operational guidance. lacks actionable decision logic and error handling.

humanizer detects and removes ai-generated text patterns to restore natural voice and personality to writing, guided by wikipedia cleanup standards.

mobile-design provides philosophy and audit tooling for mobile-first development, but lacks actionable procedures, concrete decision frameworks, and explicit outcomes for touch interaction patterns or platform-specific conventions.

senior-architect advertises three automation scripts for system design and dependency analysis across multiple tech stacks, but provides no actionable workflows, decision procedures, or concrete examples.

copy-editing covers systematic improvement of marketing copy through focused editorial passes. triggers on user requests for editing, review, or feedback on existing marketing content.

browser-automation covers web testing and scraping with incomplete guidance on selector choice and wait strategies, but the file cuts off mid-sentence and lacks actionable procedures.

senior-secops claims comprehensive application security coverage but the skill.md is incomplete stub with no actual procedure, decision logic, or outcome contracts defined.

file-organizer identifies trigger scenarios for folder cleanup but lacks actionable procedure, decision logic, and failure handling. primary value is use-case enumeration rather than implementation guidance.

clinical-reports outlines regulatory principles for healthcare documentation across case reports, diagnostics, and trials, but lacks actionable procedures, specific triggers, and failure mode handling required for consistent skill execution.

llamaindex provides a rag framework with 300+ data connectors for document ingestion and indexing, but the skill definition lacks actionable procedures, decision logic, and failure handling.

langchain is a framework for assembling llm applications using agents, chains, and rag. it abstracts across multiple providers and integrations but lacks actionable skill procedures.

api-patterns advertises design principles and decision-making for rest vs graphql vs trpc, but provides only headers and a content map placeholder. no actual procedures, decision logic, or worked examples present.

using-superpowers documents a meta-rule requiring skill invocation before responding to any user message, enforced via flowchart and red-flag heuristics, but lacks concrete inputs, decision criteria, or failure modes.

senior-data-engineer describes broad data infrastructure domains and tool families but lacks actionable procedures, decision logic, or concrete skill invocation paths for an ai agent.

database-schema-designer provides schema generation from natural language descriptions but lacks procedural depth, edge case handling, and concrete implementation guidance needed for production use.

typescript-expert routes to specialized subagents and claims to analyze project setup, but provides no actionable steps, decision logic, or defined outputs. the skill is a stub.

Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies,…

Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS. Includes component…

senior-qa — an installable skill for AI agents, published by davila7/claude-code-templates.

marketing-strategy-pmm — an installable skill for AI agents, published by davila7/claude-code-templates.

mermaid-diagram-specialist — an installable skill for AI agents, published by davila7/claude-code-templates.

scientific-visualization — an installable skill for AI agents, published by davila7/claude-code-templates.

senior-devops — an installable skill for AI agents, published by davila7/claude-code-templates.

whisper — an installable skill for AI agents, published by davila7/claude-code-templates.

Expert knowledge for deploying to Vercel with Next.js Use when: vercel, deploy, deployment, hosting, production.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use…

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance,…

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII…

Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced…

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces.…

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is…

Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are…

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B -…

Use when executing implementation plans with independent tasks in the current session

|

Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types…

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are…

Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or…

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT…

PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.

Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's…

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML…

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost…

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM…

Systematic error diagnosis and resolution using first-principle analysis. Use when encountering any error message, stack trace, or unexpected behavior.…

Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality.…

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires…

When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or…

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures,…

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for…

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific…

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical…

Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and…

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses…

gguf-quantization — an installable skill for AI agents, published by davila7/claude-code-templates.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses…

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or…

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art,…

Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for…

Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack,…

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic…

Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use…

Generate comprehensive, developer-friendly API documentation from code, including endpoints, parameters, examples, and best practices

planning-with-files — an installable skill for AI agents, published by davila7/claude-code-templates.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check…

Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model…

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site…

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and…

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic…

Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media…

Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making…

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term…

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython…

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web…

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment,…

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple…

Senior Quality Documentation Manager for comprehensive documentation control and regulatory document review. Provides document management system design, change…

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts,…

Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates…

Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity…

Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project…

Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks…

Search Engine Optimization specialist for content strategy, technical SEO, keyword research, and ranking improvements. Use when optimizing website content,…

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you…

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial…

scientific-critical-thinking — an installable skill for AI agents, published by davila7/claude-code-templates.

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM,…